Abstract: A key-value storage device includes a non-volatile memory and a controller. A method of operating the key-value storage device includes: receiving, from a host, information regarding at least one of a random region, comprising random bits, and a non-random region each included in a key; receiving, from the host, a first command including a first key; generating, based on the received information, a mapping index of a mapping table from first bits, the first bits corresponding to at least some of the random bits included in the first key; and controlling an operation for the non-volatile memory, according to the first command, by using the mapping table.

Abstract: A data storage device includes a non-volatile memory, including a first region and a second region different from the first region, and a controller which stores first and second data in a first region of the non-volatile memory. The first region of the non-volatile memory includes first and second storage regions. A part of the first data is stored in the first storage region, and another part of the first data is stored in the second storage region. The second data is stored in the second storage region, and an offset value of the second storage region in which the second data is started is stored in the second region of the non-volatile memory.

Abstract: A redundant array of independent disks (RAID) storage system includes a plurality of storage devices that perform an erase operation according to a plurality of erase unit sizes. A RAID controller controls the plurality of storage devices based on a RAID environment. The RAID controller adjusts the erase unit sizes with respect to at least some of the plurality of storage devices, respectively.

Abstract: A storage device includes multiple memory devices and a memory controller. The memory controller receives, from a host, values corresponding to data stored in the memory devices and keys for identifying the values, generates parities for inspecting the data for any errors based on the values, and manages key-value mapping information regarding a correspondence between the values and the keys. The memory devices include a first memory device and a second memory device, which store the values and the keys, and a third memory device, which stores parity values calculated from the values and a parity value header for managing the parity values.

Abstract: A method of operating a storage device including at least one nonvolatile storage and a storage controller configured to control the nonvolatile storage. A first type of request, original data and a first request information associated with the original data are received, in the storage controller, from an external host device, a compression operation to compress the original data to generate compressed data is performed in the storage controller, in response to the first type of request, and a write operation to write the compressed data in a data storage area of the nonvolatile storage is performed in the storage controller. The data storage area of the nonvolatile storage may store the first request information associated with the original data. The external host may manage mapping information in the form of a mapping table associated with compression/decompression at the storage device.

Abstract: A data storage device includes a non-volatile memory, including a first region and a second region different from the first region, and a controller which stores first and second data in a first region of the non-volatile memory. The first region of the non-volatile memory includes first and second storage regions. A part of the first data is stored in the first storage region, and another part of the first data is stored in the second storage region. The second data is stored in the second storage region, and an offset value of the second storage region in which the second data is started is stored in the second region of the non-volatile memory.

Abstract: A redundant array of inexpensive disks (RAID) system including nonvolatile memory and an operating method of the same is provided. A nonvolatile memory device implemented as a RAID and including a plurality of first memory chips, which store data chunks, and a second memory chip, in which spare memory regions are defined. A RAID controller controls RAID operations and a rebuild operation of the nonvolatile memory device. The RAID controller monitors a failure probability of each of the first memory chips, and in response to detecting a failure probability of two or more first memory chips that satisfies a predefined threshold value, a first rebuild on data stored in each of the first memory chips is performed to store the data in the second memory chip. A second rebuild on data stored in the first memory chip having the failure using data stored in the second memory chip.

Abstract: A storage device comprises a plurality of memory devices, and a memory controller receiving, from a host, values corresponding to data stored in the plurality of memory devices and keys for identifying the values, generating parities for inspecting the data for any errors based on the values, and managing key-value mapping information regarding a correspondence between the values and the keys, wherein the plurality of memory devices include first and second memory devices, which store the values and the keys, and a third memory device, which stores parity values calculated from the values and a parity value header for managing the parity values.

Abstract: Provided is a RAID system that includes a memory device including a plurality of nonvolatile memories storing data chunks and first and second parity bits corresponding to the data chunks, a RAID controller configured to control a RAID operation and a rebuild operation of the memory device, and a host configured to communicate with the RAID controller at an input/output (I/O) rate. The RAID controller is configured to perform a first rebuild operation using the first parity bit and a first policy having a first rebuild rate, to perform a second rebuild operation using the first and second parity bits and a second policy having a second rebuild rate, to apply a first sub-rate as the first rebuild rate until the I/O rate reaches a predetermined value, and to apply a second sub-rate as the first rebuild rate when the I/O rate is greater than the predetermined value.

Abstract: A key-value storage device includes a non-volatile memory and a controller. A method of operating the key-value storage device includes: receiving, from a host, information regarding at least one of a random region, comprising random bits, and a non-random region each included in a key; receiving, from the host, a first command including a first key; generating, based on the received information, a mapping index of a mapping table from first bits, the first bits corresponding to at least some of the random bits included in the first key; and controlling an operation for the non-volatile memory, according to the first command, by using the mapping table.

Abstract: A storage controller includes a co-access pattern mining unit configured to detect co-access patterns of data co-accessed during a particular time duration and to generate co-access groups including a plurality of pieces of data complying with the co-access patterns. The storage controller further include a co-access group matching unit configured to select a co-access group matched with read-requested data, among the generated co-access groups, and a data placement unit configured to store the data included in the selected co-access group in a pre-fetch buffer.

Abstract: The method of operating a storage system includes executing a storage service providing storage of a volume unit to at least one host device, in which the volume includes a first volume and a second volume. The method includes giving a first priority and a second priority lower than the first priority to the first volume and the second volume, respectively, and recovering meta-data for the first volume having the first priority when the storage service is stopped. The method includes starting the storage service using the recovered meta-data for the first volume, and recovering meta-data for the second volume having the second priority.

Abstract: Provided are a method and a system for transmitting data between storage devices over peer-to-peer (P2P) connections of peripheral component interconnect-express (PCIe). The method, performed when a first storage device receives a data request from a host, includes caching data of another storage device via PCIe connection in response to the data request, and transmitting the cached data to the host. The first storage device is configured to convert a logical address received with the data request to a physical address of a memory region of a second storage device, to store data transmitted from the second storage device via the PCIe connection in a second data cache according to the converted physical address, and to perform a cache replacement scheme for the data stored in the second data cache.

Abstract: A data storage device includes a nonvolatile memory arranged in drives and stripes, a buffer storing state information for each of the stripes, and a memory controller including a redundant array of independent disks (RAID) controller that operates in a spare region mode and performs data recovery using garbage collection based on the state information. The state information includes a first state indicating that none of the drives has malfunctioned, a second state indicating one of the drives has malfunctioned, and a third state indicating that data/parity stored in a malfunctioning drive has been recovered.

Abstract: An operating method of a memory system including a storage array including a plurality of segments and a first server node and a second server node allocating and managing the plurality of segments includes: requesting, via the first server node, load information from the second server node before performing a memory operation; receiving, via the first server node, the load information from the second server node and comparing load information of the first server node with the load information of the second server node; performing, via the first server node, a load balancing operation, based on a comparison result; and performing, via the first server node, a segment dynamic allocation operation regarding the storage array, the segment dynamic allocation operation matching the load balancing operation.

Abstract: A data mirroring control apparatus includes a command distributing unit configured to transmit a first write command to a plurality of mirroring storage devices, the first write command including an instruction for data requested by a host to be written; and a memory lock setting unit configured to set a memory lock on the data requested by the host to be written among data stored in a host memory and configured to release the memory lock on the data after the data with the memory lock is written to the plurality of mirroring storage devices.

Abstract: A deduplication method using data association information includes extracting information about a target file and at least one reference file associated with the target file as association information before duplication determination is performed. The at least one reference file is identified by the association information as a comparison target set for comparison when the duplication determination of the target file is performed. The duplication determination is performed with the target file with respect to the at least one reference file in the selected comparison target set.

Abstract: Data deduplication is performed by separating data into a plurality of data chunks that correspond to first through Nth positions and include symbols, calculating discrimination indices of the positions using frequencies of the symbols in the different positions; arranging the order of the positions based on values of the discrimination indices; and generating fingerprints of the data through combination of data chunks that correspond to a number of the positions, based on the arranged order of the positions.

Abstract: Processing an adaptive interrupt includes selectively setting an input/output (I/O) device in a computing system to an adaptive masking mode when at least one factor value of the at least one I/O device regarding a workload of the computing system exceeds a first threshold condition. Processing the adaptive interrupt further includes performing an interrupt masking process, where an interrupts generated by an I/O device set to the adaptive masking mode are prevented from being output when a time interval between I/O submission events of the I/O device is less than a first threshold value. The adaptive interrupt may be processed by an adaptive interrupt processing module (AIPM). The AIPM may be included in various portions of the computing system, including the I/O device and a host connected to the I/O device.

Abstract: A storage controller includes a co-access pattern mining unit configured to detect co-access patterns of data co-accessed during a particular time duration and to generate co-access groups including a plurality of pieces of data complying with the co-access patterns. The storage controller further include a co-access group matching unit configured to select a co-access group matched with read-requested data, among the generated co-access groups, and a data placement unit configured to store the data included in the selected co-access group in a pre-fetch buffer.